Papers › Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

29 Mar 2018CVPR 2018 6arXiv:1803.11285archive 2025-07-28

Filip Radenović, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum

In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth. Three new protocols of varying difficulty are introduced. The protocols allow fair comparison between different methods, including those using a dataset pre-processing stage. For each dataset, 15 new challenging queries are introduced. Finally, a new set of 1M hard, semi-automatically cleaned distractors is selected. An extensive comparison of the state-of-the-art methods is performed on the new benchmark. Different types of methods are evaluated, ranging from local-feature-based to modern CNN based methods. The best results are achieved by taking the best of the two worlds. Most importantly, image retrieval appears far from being solved.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingImage RetrievalRetrieval

Datasets

Introduced by this paper, per the archive.

ROxford

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval ROxford (Hard) HesAff–rSIFT–HQE+SP mAP 49.7 #10 of 23 Archive leaderboard report
Image Retrieval ROxford (Hard) HesAff–rSIFT–HQE mAP 41.3 #12 of 23 Archive leaderboard report
Image Retrieval ROxford (Hard) HesAff–rSIFT–ASMK*+SP mAP 36.7 #14 of 23 Archive leaderboard report
Image Retrieval ROxford (Hard) HesAff–rSIFT–ASMK* mAP 36.4 #15 of 23 Archive leaderboard report
Image Retrieval ROxford (Hard) HesAff–rSIFT–SMK*+SP mAP 35.8 #16 of 23 Archive leaderboard report
Image Retrieval ROxford (Hard) HesAff–rSIFT–SMK* mAP 35.4 #17 of 23 Archive leaderboard report
Image Retrieval ROxford (Hard) HesAff–rSIFT–VLAD mAP 13.2 #22 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) HesAff–rSIFT–HQE+SP mAP 71.3 #9 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) HesAff–rSIFT–HQE mAP 66.3 #11 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) HesAff–rSIFT–ASMK*+SP mAP 60.6 #15 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) HesAff–rSIFT–ASMK* mAP 60.4 #16 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) HesAff–rSIFT–SMK*+SP mAP 59.8 #17 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) HesAff–rSIFT–SMK* mAP 59.4 #18 of 23 Archive leaderboard report
Image Retrieval ROxford (Medium) HesAff–rSIFT–VLAD mAP 33.9 #23 of 23 Archive leaderboard report
Image Retrieval ROxford Medium without fine-tuning HesAff–rSIFT–VLAD Average mAP 33.9 #1 of 1 Archive leaderboard report
Image Retrieval RParis (Hard) HesAff–rSIFT–HQE+SP mAP 45.1 #15 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) HesAff–rSIFT–HQE mAP 44.7 #17 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) HesAff–rSIFT–ASMK*+SP mAP 35.0 #19 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) HesAff–rSIFT–ASMK* mAP 34.5 #20 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) HesAff–rSIFT–SMK*+SP mAP 31.3 #21 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) HesAff–rSIFT–SMK* mAP 31.2 #22 of 23 Archive leaderboard report
Image Retrieval RParis (Hard) HesAff–rSIFT–VLAD mAP 17.5 #23 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) HesAff–rSIFT–HQE+SP mAP 70.2 #15 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) HesAff–rSIFT–HQE mAP 68.9 #17 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) HesAff–rSIFT–ASMK*+SP mAP 61.4 #19 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) HesAff–rSIFT–ASMK* mAP 61.2 #20 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) HesAff–rSIFT–SMK*+SP mAP 59.2 #21 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) HesAff–rSIFT–SMK* mAP 59.0 #22 of 23 Archive leaderboard report
Image Retrieval RParis (Medium) HesAff–rSIFT–VLAD mAP 43.6 #23 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections